README.md

---
tags:
- text-to-image
- lora
- diffusers
- flux
base_model: black-forest-labs/FLUX.1-dev
license: creativeml-openrail-m
library_name: diffusers
---

# Van Lang University Logo

LoRA Adapter for [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) trained on  15 pictures of Van Lang University Logo with [ai-toolkit](https://github.com/ostris/ai-toolkit/tree/main)


## Trigger words
You should use `VLU` to trigger the image generation. The trigger phrase `VLU Logo with 'Van Lang University' text printed on [material]. 


# Model Details

**Some Examples**

<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(1).jpg" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(2).jpg" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(3).jpg" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(1).png" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(2).png" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(3).png" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(4).png" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(4).png" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(6).png" width=512>
<img src="https://huggingface.co/dtthanh/vlu_logo/resolve/main/VLU_logo%20(7).png" width=512>

# Usage

With diffusers package  
*Note: FLUX uses ~70GBvram when loaded directly with diffusers*  
*Note: Recommended to load at ~70% scale for best results*  

```python
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev")
pipeline.load_lora_weights('dtthanh/vlu_logo', weight_name='lora.safetensors')
pipeline.to("cuda")

prompt = "a photo of a female student with red polo on that there is VLU Logo with 'Van Lang University' text printed. backgound is a class."

out = pipeline(
    prompt=prompt,
    guidance_scale=3.5,
    num_inference_steps=20,
    cross_attention_kwargs={"scale": 0.7}
).images[0]

out.save("vlulogo.png")
```

# Additional Details

Please see base model page [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) for all details on appropriate usage, licensing, and more.